Translation Error Detection as Rationale Extraction
Marina Fomicheva, Lucia Specia, Νικόλαος Αλέτρας · Findings of the Association for Computational Linguistics: ACL 2022 · 2022
Recent Quality Estimation (QE) models based on multilingual pre-trained representations have achieved very competitive results in predicting the overall quality of translated sentences.However, detecting specifically which translated words are incorrect is a more challenging task, especially when dealing with limited amounts of training data.We hypothesize that, not unlike humans, successful QE models rely on translation errors to predict overall sentence quality.By exploring a set of feature attribution methods that assign relevance scores to the inputs to explain model predictions, we study the behaviour of state-of-theart sentence-level QE models and show that explanations (i.e.rationales) extracted from these models can indeed be used to detect translation errors.We therefore (i) introduce a novel semi-supervised method for word-level QE; and (ii) propose to use the QE task as a new benchmark for evaluating the plausibility of feature attribution, i.e. how interpretable model explanations are to humans.